# Xberg

> Full content intelligence engine: extract text, tables, entities, and embeddings from 101 formats with OCR, transcription, code intelligence, and LLM integration. Native bindings for 15 languages.

## Documentation Sets

- [Abridged documentation](https://docs.xberg.io/llms-small.txt): a compact version of the documentation for Xberg, with non-essential content removed
- [Complete documentation](https://docs.xberg.io/llms-full.txt): the full documentation for Xberg
- [Get Started](https://docs.xberg.io/_llms-txt/get-started.txt): Installation and quick-start guides.
- [Guides](https://docs.xberg.io/_llms-txt/guides.txt): Task-oriented guides: extraction, configuration, OCR, chunking, embeddings, transcription, structured extraction, code intelligence, and deployment.
- [Concepts](https://docs.xberg.io/_llms-txt/concepts.txt): Architecture, the extraction pipeline, and the plugin system.
- [Integrations](https://docs.xberg.io/_llms-txt/integrations.txt): Connecting Xberg to Open WebUI, SurrealDB, and other tools.
- [Reference](https://docs.xberg.io/_llms-txt/reference.txt): Per-language API docs, configuration schema, types, errors, formats, and CLI/MCP reference.
- [More](https://docs.xberg.io/_llms-txt/more.txt): Migration, changelog, contributing, and ecosystem.

## Notes

- The complete documentation includes all content from the official documentation
- The content is automatically generated from the same source as the official documentation

## Optional

- [GitHub](https://github.com/xberg-io/xberg): Source code and issues